Summary
Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for magnetic resonance (MR) image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into clustering algorithms, and they generally have difficulties when INU reaches high amplitudes. This study proposes a multiple stage fuzzy c-means (FCM) clustering based algorithm for the estimation and compensation of INU, by modelling it as a slowly varying additive or multiplicative noise. The slowly varying behaviour of the bias or gain field is assured by a smoothing filter that performs a context dependent averaging, controlled by a morphological criterion. The segmentation is also supported by a prefiltering technique for Gaussian and impulse noise elimination. The experiments using 2-D synthetic phantoms and real MR images indicate that the proposed method provides accurate segmentation. The resulting segmentation and fuzzy membership values can serve as excellent support for 3-D registration and surface reconstruction techniques.
See the full content of this document
Extract
Intensity Inhomogeneity Correction and Segmentation of Magnetic Resonance Images Using a Multi-Stage Fuzzy Clustering Approach
(ProQuest: ... denotes formulae omitted.)
1. IntroductionMedical imaging based on magnetic resonance (MRI) is a very popular technique, mainly because of its high resolution and contrast, which represent great advantages above other diagnostic imaging modalities. Besides all these good properties, MRI also suffers from three considerable obstacles: high frequency noises (mixture of Gaussian and impulse noises), partial volume effect (pixels containing at least two types of tissues), and intensity inhomogeneity [21]. This latter one, also known as intensity non-uniformity (or INU artefact), manifests as a spatially slowly varying function that makes pixels belonging to the same tissue be observed having different intensities. In order to produce a correct segmentation or registration of MR images, the INU artefact needs to be modelled and compensated.INU has two different types of sources: those related to the MRI device, and those related to the imaged patient's shape, position, structure and orientation [20]. While the first type of source has efficient compensation and calibration methods, INU artefacts of the second type are much more difficult to handle [30] . A widely used technique, handling mostly the first type ...See the full content of this document
Sponsored links
